Handwritten Numbers And Characters Recognition Using Machine Learning Algorithms

NIET Journal of Engineering & Technology (NIETJET)
Volume 4, Issue Winter 2015 ISSN: 2229-5828 (Print)
21 | Page
Publisher: Noida Institute of Engineering & Technology,
19, Knowledge Park-II, Institutional Area, Greater Noida (UP), India.
Abstract: Recently, in the whole world, enormous electric energy is consumed by the street lights. These lights are
automatically turn on when it becomes dark and automatically turn off when it becomes bright. This is the huge waste of
energy in the whole world and should be controlled. Street lights in India consume approximately 20-40% of the electrical
energy produced in the entirenation and the demand for electricity in recent years has increased day by day. In this paper,
smart street light is introduced which is IoT based, it aims to automate the light system, also, LEDs are used to assures the
low power consumption. The operation of this system is to maintain the intensity of streetlights to 40% of the maximum
intensity if no vehicles passing through the road. Electricity theft problem is also address in this paper uses a sudden signal
of power drop or phase drop to detect the exact pole at which electricity theft is happening or if that particular street light is
faulty. Moreover, all these data are shared through IoT about and can be controlled and monitored by a mobile application.
Keywords –Smart Street Light , IoT, Arduino Microcontroller, sensors.
1. INTRODUCTION
Street light systems are a major part of today’s urbanization, about 80% of India’s population uses the vehicle and
hence streetlights area necessity of smart city. Existing streetlights have been seen as a major power consumption
unit. So, to save electrical energy, smart street lights are exceedingly important. Many street lights still require
manual monitoring, which can be a tedious task [1]. Technically speaking, power losses are divided into two
categories: technical losses and non-technical losses. Power quality issues, such as too long network cables, sloppy
wire connections, worn out cubicles, and the use of worn out wires, all contribute to technical losses. Non-technical
factors include electricity theft, which causes load fluctuations if electricity usage is increased. The transformer
suffers losses as a result of this. Thus to observe this problem the identification can be done either physically, or to
keep the track on the consumption of customer. Losses involving electricity theft are a major concern in our country
and many others. In past few years IoT has become a rising technology to share and control data over the internet
and that is how these street lights can be controlled from just a button on a mobile application [2]. Therefore, it has
become important to overcome the existing system problems and design a new system that saves the maximum
amount of electricity and is easy to control without any manual help.
2. BACKGROUND STUDY
Many papers with similar topics are taken as a suggestions and used for understanding smart streetlight, indicating
that everything has its advantages and disadvantages and its own concepts and b the ories to make a streetlight smart
by using different micro controller, sensors and software: Based on paper Smart Street Light System using IoT [1]
automation can save a huge amount of energy, energy conservation is made easy with the use of sensors, The
Internet of Things (IoT) is an assortment of interrelated preparing devices, mechanical or virtual
machines,articles,animalsandindividualsthathavefascinatingidentifiers(UIDs) and the ability to move information
over a framework without expecting of human-to-human. IoT is used to gather an accurate real time field data which
can be used for future references. Based on IoT Based Smart Street Lightning System [2] Data from street lights are
stored by IoT hence they can be used as a multi-functional element, intensity of the road light can be controlled,
accident prevention, smoke detection, over speeding can be kept in check through sensors. Based on A Study on
IoT based Smart Street Light Systems [3] Smart Street Lighting System faces the major problems like Crime
Advance Street Lighting System for
Smart City
Nidhi Sharma1
, Kamal Bhatia1
, Amit Kumar Yadav1
1
Assistant Professor, Department of Electronics& Communication Engineering, Noida Institute of
Engineering & Technology, Greater Noida 201306 India

22 | Page
detection, Energy wastage, disposal of in can descent lamps, maintenance cost etc., This system ensures traffic
safety and the security of the people and can stop burglaries and further intimidations by sharing the data through
IoT and using sensors .Based on A Survey on Automatic Street Lightning [4] Light dependent resistors
areusedwiththemicrocontrollerArduinoUNOtooperatethelightsautomaticallyduring rain, day and night to avoid
manual labor leading to energy conservation and saving cost on manual labor.BasedonIntelligentStreet-
LightSystemusingArduinoUNO[5]Arduinomicrocontrollerisusedalongwithlightdependentresistortocontrolthelight
saccording to the natural light present in the surrounding. This technology can also be directed towards other things
like head lights, street light, park lights, industrial lights etc. Based on Smart street light using Arduino [6] The
LEDs adjust to the surrounding’s natural light and is fully turned on when it’s completely dark, the street lights also
have LED displays which gives the current weather report.
3. EXISTING SYSTEM DRAWBACK
 In existing street light halogen bulbs are used which are not very eco-friendly and consume lot of power.
 Some existing system require manual monitoring of streetlights which can be at edious task as well.
 Lightsturnon/offataclockcyclewhichleadstoelectricitywastagewhenthesunrisesearlyandsetslateduring
summers.
 Lights are on even at the places where there is no need, leading to electricity wastage.
 Thereisnoeasyandfastwaytodetectfaultylightsortodetectelectricitytheftbesidesphysicalinception.
4. PROPOSED SYSTEM
This paper is based on street light development which will help to develop a smart street light. This proposed system
does not consist of any expensive hardware and is easier to replace in case of failure. The light will sense the
brightness, also detect any moment in the environment and adjust the intensity as per the same, Sensors are affixed
to sense the luminosity and moment detection. The data of street lights i.e. its power consumption will be monitored
by IoT which helps in detecting power loss and all this can be controlled by a mobile application just at the tip of
your hand. The proposed system will reduce most drawbacks of the existing system. The
proposedsystemaimstouseLEDsinplaceofconventionallyusedhalogenbulbsorHIDbulbs.Thisensures100%Automato
n (inexceptiontoperiodic maintenance).
Figure-1: System Architecture

23 | Page
5. PROPOSED CIRCUITCOMPONENTS AND ITS CIRCUIT
5.1 ARDUINOUNOR3:
The Arduino UNO is the project's brain. It has 14 digital input/output pins, 6 analogue inputs a 16 MHz ceramic
resonator (CSTCE16M0V53-R0), a USB connection, a power jack, an ICSP header, and are set button.It comes
witheverythingyouneedtosupportthemicrocontroller;allyouhavetodoisconnectthecomputertothecontrollerusingaUS
Bcableorpoweritwitha AC-to-DC adapter or battery to get It running.
5.2 IR Sensors:
IR Sensor is a electronic component which is used to sense some characteristics from its surrounding by either
emitting infrared radiations or detecting them. It can also measure heat and detect motion Infrared radiations are
invisible to human eyes.
5.3 Phototransistor:
The phototransistor is a semiconductor device that changes the current flow between emitter and collector according
to the light levels. The phototransistor is more sensitive in view of the gain provided by the fact that it is a bipolar
transistor.
5.4 LED:
When current flows through a light-emitting diode, it produces light. Electrons recombine with electron holes in the
semiconductor, releasing energy in the form of photons. The energy required for electrons to cross these
miconductor's band gap determines the color of light(corresponding to the energy of photons).The use of white light
is obtained .Multiples emiconductors or a layer of light-emitting phosphor on the semiconductor device are used to
produce white light.
5.5 Node MCU:
TheNodeMCUplatformisalow-costopensourceIoTplatform.Itoriginallyincludedfirmware that ran on Espressif
Systems- ESP8266 Wi-Fi SoC and hardware that was based ontheESP-12 module.
ESP8266 Wi-Fi SoC and hardware that was based ontheESP-12 module.
Fig.2 IR sensor (amazon. In ) Fig.3 LED light

24 | Page
Fig.4 Photo transistor Fig.5 Node MCU
The basic model of the Smart Street Light consists of an Arduino UNO R3 which is a micro controller board
established on the ATmega328P. It has 14 digital input/output pins, 6 analogue inputs, a 16 MH zceramic
resonator(CSTCE16M0V53-R0), a USB connection, a power jack, an ICSP header, and are set button. It comes
with everything you need to support the microcontroller; all you have to do is connect the computer to the controller

25 | Page
using a USB cable or power it with a AC-to-DC adapter or battery to get it running and IR Sensor is an electronic
component which is used to sense some characteristics from its surrounding by either emitting infrared radiations
or detecting them. It can also measure heat and detect motion. Infrared radiations are invisible to human eyes. IR
Sensors are connected to breadboard according to the circuit diagram along with the LED Lights.
TheIRSensoralongwithLEDareconnectedtoArduinowheretheinputfromtheIRsensorisgivento the analog input of the
Arduino pin(A0-A5) and the output is given to the LED from Arduino pin(D0-D15).
The Node MCU platform is a low-cost open source IoT platform. It originally included firmware
thatranonEspressifSystems-ESP8266 Wi-Fi So C and hardware that was based ontheESP-12 module.
Blynk Software is platform that help us to connect our model with IoT and Mobile App. The Blynk App will control
the Smart Street Light model through Node MCU.
6. FUTURE ENHANCEMENTS
Smart street lights can be used for surveillance purpose. i.e. the lights can be installed with cameras with inbuilt
AIfunctionwhichcanidentifycarcrashoranyunethicalactivitieshappeningInthesurroundings.Solarpanelscanbeinstalle
dtopowerthestreet lights.
Piezoelectricitycanbeusedtopowerthestreetlightsonafootpathorrunning/joggingarea(Piezoelectricity is the electric
charge that acquire in certain solid materials in response to applied mechanical stress. So, when a person is walking
or running on any piezoelectric generating surface then electrical energy can be produced).
7. CONCLUSION
The existing system use halogen bulb which are not very eco-friendly and consume lot of power. The solution to
energy conservation is to introduce a system that could sense brightness levels and moment in the environment and
act accordingly, so that the intensity of street lights is not affected by seasonal changes. LED scan also be used
instead of HID lamps be cause they can be dimmed. Electricity the ft and power loss is a major concern hence its
detection is required in an easier and faster way.

26 | Page
References
[1]. YusakuFujii , NoriakiYoshiura, Akihiro Takita, NaoyaOhta, “Smart street light system with energy saving
function based on the sensor Network”, Conference: Proceedings of the fourth international conference on
Future energy systems, January 2013.
[2]. Pilar Elejoste1 , Ignacio Angulo 1 , AsierPerallos 1,*, AitorChertudi , An Easy to Deploy Street Light Control
System Based on Wireless Communication and LED Technology, Sensors, May 2013.
[3]. Samir A. Elsagheer Mohamed , “Smart Street Lighting Control and Monitoring System for Electrical
Power Saving by Using VANET”,International Journal of Communications, Network and System
Sciences > Vol.6 No.8, August 2013
[4]. B. Subramanyam, K. B. Reddy, P. K. Reddy, Design and Development of Intelligent Wireless Street Light
Control and Monitoring System Along With GUI”, International Journal of Engineering Research and
Applications (IJERA), August 2013.
[5]. Reinhard Mu¨ llner and Andreas Riener, “An energy efficient pedestrian aware Smart Street Lighting system”,
International Journal of Pervasive Computing and Communications · June 2011.
[6]. Aishwarya.N. Patil, Ashwin Tripathi, S. A. Fanan, “Intelligent Street-Light System using Arduino UNO”,
International Journal of Engineering Science and Computing IJESC Volume7IssueNo.5, 2017.

Handwritten Numbers And Characters Recognition Using Machine Learning Algorithms

More Related Content

Similar to Handwritten Numbers And Characters Recognition Using Machine Learning Algorithms (20)

More from NIET Journal of Engineering & Technology (NIETJET) (20)

Recently uploaded (20)

Handwritten Numbers And Characters Recognition Using Machine Learning Algorithms